Elasticsearch 聚合的作用范围及排序

原创

ghostwritten 2022-05-31 00:21:57 博主文章分类：elk ©著作权

文章标签 elasticsearch 大数据 java javascript 插入数据 文章分类 数据结构与算法人工智能

©著作权归作者所有：来自51CTO博客作者ghostwritten的原创作品，请联系作者获取转载授权，否则将追究法律责任

文章目录

1. 聚合的作用范围
2. demo

2.1 定义索引并插入数据
2.2 Query
2.3 Filter
2.4 Post_Filter
2.5 global
2.6 排序 order

1. 聚合的作用范围

ES 聚合分析的默认作用范围是 query 的查询结果集

同时 ES 还支持以下方式改变聚合的作用范围

Filter
Post_Filter
Global

2. demo

2.1 定义索引并插入数据

DELETE /employees
PUT /employees/
{
  "mappings" : {
      "properties" : {
        "age" : {
          "type" : "integer"
        },
        "gender" : {
          "type" : "keyword"
        },
        "job" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 50
            }
          }
        },
        "name" : {
          "type" : "keyword"
        },
        "salary" : {
          "type" : "integer"
        }
      }
    }
}

PUT /employees/_bulk
{ "index" : {  "_id" : "1" } }
{ "name" : "Emma","age":32,"job":"Product Manager","gender":"female","salary":35000 }
{ "index" : {  "_id" : "2" } }
{ "name" : "Underwood","age":41,"job":"Dev Manager","gender":"male","salary": 50000}
{ "index" : {  "_id" : "3" } }
{ "name" : "Tran","age":25,"job":"Web Designer","gender":"male","salary":18000 }
{ "index" : {  "_id" : "4" } }
{ "name" : "Rivera","age":26,"job":"Web Designer","gender":"female","salary": 22000}
{ "index" : {  "_id" : "5" } }
{ "name" : "Rose","age":25,"job":"QA","gender":"female","salary":18000 }
{ "index" : {  "_id" : "6" } }
{ "name" : "Lucy","age":31,"job":"QA","gender":"female","salary": 25000}
{ "index" : {  "_id" : "7" } }
{ "name" : "Byrd","age":27,"job":"QA","gender":"male","salary":20000 }
{ "index" : {  "_id" : "8" } }
{ "name" : "Foster","age":27,"job":"Java Programmer","gender":"male","salary": 20000}
{ "index" : {  "_id" : "9" } }
{ "name" : "Gregory","age":32,"job":"Java Programmer","gender":"male","salary":22000 }
{ "index" : {  "_id" : "10" } }
{ "name" : "Bryant","age":20,"job":"Java Programmer","gender":"male","salary": 9000}
{ "index" : {  "_id" : "11" } }
{ "name" : "Jenny","age":36,"job":"Java Programmer","gender":"female","salary":38000 }
{ "index" : {  "_id" : "12" } }
{ "name" : "Mcdonald","age":31,"job":"Java Programmer","gender":"male","salary": 32000}
{ "index" : {  "_id" : "13" } }
{ "name" : "Jonthna","age":30,"job":"Java Programmer","gender":"female","salary":30000 }
{ "index" : {  "_id" : "14" } }
{ "name" : "Marshall","age":32,"job":"Javascript Programmer","gender":"male","salary": 25000}
{ "index" : {  "_id" : "15" } }
{ "name" : "King","age":33,"job":"Java Programmer","gender":"male","salary":28000 }
{ "index" : {  "_id" : "16" } }
{ "name" : "Mccarthy","age":21,"job":"Javascript Programmer","gender":"male","salary": 16000}
{ "index" : {  "_id" : "17" } }
{ "name" : "Goodwin","age":25,"job":"Javascript Programmer","gender":"male","salary": 16000}
{ "index" : {  "_id" : "18" } }
{ "name" : "Catherine","age":29,"job":"Javascript Programmer","gender":"female","salary": 20000}
{ "index" : {  "_id" : "19" } }
{ "name" : "Boone","age":30,"job":"DBA","gender":"male","salary": 30000}
{ "index" : {  "_id" : "20" } }
{ "name" : "Kathy","age":29,"job":"DBA","gender":"female","salary": 20000}

2.2 Query

POST employees/_search
{
  "size": 0,
  "query": {
    "range": {
      "age": {
        "gte": 20
      }
    }
  },
  "aggs": {
    "jobs": {
      "terms": {
        "field":"job.keyword"
        
      }
    }
  }
}

返回输出：

{
  "took" : 2,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 20,
      "relation" : "eq"
    },
    "max_score" : null,
    "hits" : [ ]
  },
  "aggregations" : {
    "jobs" : {
      "doc_count_error_upper_bound" : 0,
      "sum_other_doc_count" : 0,
      "buckets" : [
        {
          "key" : "Java Programmer",
          "doc_count" : 7
        },
        {
          "key" : "Javascript Programmer",
          "doc_count" : 4
        },
        {
          "key" : "QA",
          "doc_count" : 3
        },
        {
          "key" : "DBA",
          "doc_count" : 2
        },
        {
          "key" : "Web Designer",
          "doc_count" : 2
        },
        {
          "key" : "Dev Manager",
          "doc_count" : 1
        },
        {
          "key" : "Product Manager",
          "doc_count" : 1
        }
      ]
    }
  }
}

2.3 Filter

POST employees/_search
{
  "size": 0,
  "aggs": {
    "older_person": {
      "filter":{
        "range":{
          "age":{
            "from":35
          }
        }
      },
      "aggs":{
         "jobs":{
           "terms": {
        "field":"job.keyword"
      }
      }
    }},
    "all_jobs": {
      "terms": {
        "field":"job.keyword"
        
      }
    }
  }
}

返回输出：

{
  "took" : 6,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 20,
      "relation" : "eq"
    },
    "max_score" : null,
    "hits" : [ ]
  },
  "aggregations" : {
    "older_person" : {
      "doc_count" : 2,
      "jobs" : {
        "doc_count_error_upper_bound" : 0,
        "sum_other_doc_count" : 0,
        "buckets" : [
          {
            "key" : "Dev Manager",
            "doc_count" : 1
          },
          {
            "key" : "Java Programmer",
            "doc_count" : 1
          }
        ]
      }
    },
    "all_jobs" : {
      "doc_count_error_upper_bound" : 0,
      "sum_other_doc_count" : 0,
      "buckets" : [
        {
          "key" : "Java Programmer",
          "doc_count" : 7
        },
        {
          "key" : "Javascript Programmer",
          "doc_count" : 4
        },
        {
          "key" : "QA",
          "doc_count" : 3
        },
        {
          "key" : "DBA",
          "doc_count" : 2
        },
        {
          "key" : "Web Designer",
          "doc_count" : 2
        },
        {
          "key" : "Dev Manager",
          "doc_count" : 1
        },
        {
          "key" : "Product Manager",
          "doc_count" : 1
        }
      ]
    }
  }
}

2.4 Post_Filter

Post field. 一条语句，找出所有的job类型。还能找到聚合后符合条件的结果

是对聚合分析后的文档进行再次过滤
Size 无需设置为 0
使用场景
一条语句，获取聚合信息 + 获取符合条件的文档

POST employees/_search
{
  "aggs": {
    "jobs": {
      "terms": {
        "field": "job.keyword"
      }
    }
  },
  "post_filter": {
    "match": {
      "job.keyword": "Dev Manager"
    }
  }
}

返回输出：
Elasticsearch 聚合的作用范围及排序_插入数据

2.5 global

POST employees/_search
{
  "size": 0,
  "query": {
    "range": {
      "age": {
        "gte": 40
      }
    }
  },
  "aggs": {
    "jobs": {
      "terms": {
        "field":"job.keyword"
        
      }
    },
    
    "all":{
      "global":{},
      "aggs":{
        "salary_avg":{
          "avg":{
            "field":"salary"
          }
        }
      }
    }
  }
}

返回输出：

{
  "took" : 3,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 1,
      "relation" : "eq"
    },
    "max_score" : null,
    "hits" : [ ]
  },
  "aggregations" : {
    "all" : {
      "doc_count" : 20,
      "salary_avg" : {
        "value" : 24700.0
      }
    },
    "jobs" : {
      "doc_count_error_upper_bound" : 0,
      "sum_other_doc_count" : 0,
      "buckets" : [
        {
          "key" : "Dev Manager",
          "doc_count" : 1
        }
      ]
    }
  }
}

2.6 排序 order

指定 order，按照 count 和 key 排序
默认情况，按照 count 降序排序
指定 size，就能返回相应的桶

#count and key

POST employees/_search
{
  "size": 0,
  "query": {
    "range": {
      "age": {
        "gte": 20
      }
    }
  },
  "aggs": {
    "jobs": {
      "terms": {
        "field":"job.keyword",
        "order":[
          {"_count":"asc"},
          {"_key":"desc"}
          ]
        
      }
    }
  }
}

返回输出：

{
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 20,
      "relation" : "eq"
    },
    "max_score" : null,
    "hits" : [ ]
  },
  "aggregations" : {
    "jobs" : {
      "doc_count_error_upper_bound" : 0,
      "sum_other_doc_count" : 0,
      "buckets" : [
        {
          "key" : "Product Manager",
          "doc_count" : 1
        },
        {
          "key" : "Dev Manager",
          "doc_count" : 1
        },
        {
          "key" : "Web Designer",
          "doc_count" : 2
        },
        {
          "key" : "DBA",
          "doc_count" : 2
        },
        {
          "key" : "QA",
          "doc_count" : 3
        },
        {
          "key" : "Javascript Programmer",
          "doc_count" : 4
        },
        {
          "key" : "Java Programmer",
          "doc_count" : 7
        }
      ]
    }
  }
}

#排序 order
#count and key

POST employees/_search
{
  "size": 0,
  "aggs": {
    "jobs": {
      "terms": {
        "field":"job.keyword",
        "order":[  {
            "avg_salary":"desc"
          }]
        
        
      },
    "aggs": {
      "avg_salary": {
        "avg": {
          "field":"salary"
        }
      }
    }
    }
  }
}

返回输出：
Elasticsearch 聚合的作用范围及排序_大数据_02

#排序 order
#count and key

POST employees/_search
{
  "size": 0,
  "aggs": {
    "jobs": {
      "terms": {
        "field":"job.keyword",
        "order":[  {
            "stats_salary.min":"desc"
          }]
        
        
      },
    "aggs": {
      "stats_salary": {
        "stats": {
          "field":"salary"
        }
      }
    }
    }
  }
}